Search

Algorithmic Foundations of Robotics XIV. WAFR 2020, Perception systems for autonomy are most useful if they can operate within limited/predictable computing resources. Existing algorithms in robot navigation—e.g. simultaneous localization and mapping—employ concepts from filtering, fixed-lag, or incremental smoothing to find feasible inference solutions. Using factor graphs as a probabilistic modeling language, we emphasize the importance of marginalization operations on the equivalent Bayes (junction) tree. The objective is to elucidate the connection between simple tree-based message passing rules with the aforementioned state estimation approaches, and their frequently overlooked relation to direct marginalization on the Bayes tree. We characterize the inherent marginalization operation as part of the fundamental Chapman-Kolmogorov transit integrals which unifies many state-of-the-art approaches. The belief propagation model is then used to define five major tree inference strategies, with regard to computation recycling and resource constrained operation. A series of illustrative examples and results show the versatility of the method.

This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to model and sample the full posterior. By leveraging the Bayes tree, NF-iSAM enables efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the advantages of NF-iSAM over state-of-the-art point and distribution estimation algorithms using range-only SLAM problems with data association ambiguity. NF-iSAM presents superior accuracy in describing the posterior beliefs of continuous variables (e.g., position) and discrete variables (e.g., data association).

This thesis presents a sum-product inference algorithm for platform navigation called Multi-modal iSAM (incremental smoothing and mapping). Common Gaussian only likelihoods are restrictive and require a complex front-end processes to deal with non-Gaussian measurements. Instead, our approach allows the front-end to defer ambiguities with non-Gaussian measurement models. We retain the acyclic Bayes tree (and incremental update strategy) from the predecessor iSAM2 max-product algorithm [Kaess et al., IJRR 2012]. The approach propagates continuous beliefs on the Bayes (Junction) tree, which is an efficient symbolic refactorization of the nonparametric factor graph, and asymptotically approximates the underlying Chapman-Kolmogorov equations. Our method tracks dominant modes in the marginal posteriors of all variables with minimal approximation error, while suppressing almost all low likelihood modes (in a non-permanent manner). Keeping with existing inertial navigation, we present a novel, continuous-time, retroactively calibrating inertial odometry residual function, using preintegration to seamlessly incorporate pure inertial sensor measurements into a factor graph. We centralize around a factor graph (with starved graph databases) to separate elements of the navigation into an ecosystem of processes. Practical examples are included, such as how to infer multi-modal marginal posterior belief estimates for ambiguous loop closures; raw beam-formed acoustic measurements; or conventional parametric likelihoods, and others., NSF, ONR, DARPA

© 2019 IEEE. The recent success of object detection systems motivates object-based representations for robot navigation; i.e. semantic simultaneous localization and mapping (SLAM). The semantic SLAM problem can be decomposed into a discrete inference problem: determining object class labels and measurement-landmark correspondences (the data association problem), and a continuous inference problem: obtaining the set of robot poses and object locations in the environment. A solution to the semantic SLAM problem necessarily addresses this joint inference, but under ambiguous data associations this is in general a non-Gaussian inference problem, while the majority of previous work focuses on Gaussian inference. Previous solutions to data association either produce solutions between potential hypotheses or maintain multiple explicit hypotheses for each association. We propose a solution that represents hypotheses as multiple modes of an equivalent non-Gaussian sensor model. We then solve the resulting non-Gaussian inference problem using nonparametric belief propagation. We validate our approach in a simulated hallway environment under a variety of sensor noise characteristics, as well as using real data from the KITTI dataset, demonstrating improved robustness to perceptual aliasing and odometry uncertainty., Office of Naval Research (Grants N00014-18-1-2832 and N00014-16- 1-2628)

© 2020 IEEE. This paper presents a method for processing sparse, non-Gaussian multimodal data in a simultaneous localization and mapping (SLAM) framework using factor graphs. Our approach demonstrates the feasibility of using a sum-product inference strategy to recover functional belief marginals from highly non-Gaussian situations, relaxing the prolific unimodal Gaussian assumption. The method is more focused than conventional multi-hypothesis approaches, but still captures dominant modes via multi-modality. The proposed algorithm exists in a trade space that spans the anticipated uncertainty of measurement data, task-specific performance, sensor quality, and computational cost. This work leverages several major algorithm design constructs, including clique recycling, to put an upper bound on the allowable computational expense - a major challenge in non-parametric methods. To better demonstrate robustness, experimental results show the feasibility of the method on at least two of four major sources of non-Gaussian behavior: i) the first introduces a canonical range-only problem which is always underdetermined although composed exclusively from Gaussian measurements; ii) a real-world AUV dataset, demonstrating how ambiguous acoustic correlator measurements are directly incorporated into a non-Gaussian SLAM solution, while using dead reckon tethering to overcome short term computational requirements.

© 2019 IEEE. We extend the core operation of non-parametric belief propagation (NBP), also known as multi-scale sequential Gibbs sampling, to approximate products of kernel density estimated beliefs that reside on some manifold. The original algorithm, though multidimensional, implicitly assumes the beliefs to reside on the Euclidean mathbb{R}{d} space only. The proposed extension generalizes to any mixture of Riemannian manifolds, provided the primary operations - addition and subtraction - are defined. Our motivation is primarily focused on state-estimation using non-Gaussian factor graphs for multimodal simultaneous localization and mapping in robotics. The paper presents the method as well as simulation and experimental results for validation. Our implementation is publicly available and allows for expansion with user-defined manifold mixtures., Office of Naval Research (Grants N00014-18-1-2832 and N00014-16- 1-2628)

© 2019 IEEE. We extend the core operation of non-parametric belief propagation (NBP), also known as multi-scale sequential Gibbs sampling, to approximate products of kernel density estimated beliefs that reside on some manifold. The original algorithm, though multidimensional, implicitly assumes the beliefs to reside on the Euclidean mathbb{R}{d} space only. The proposed extension generalizes to any mixture of Riemannian manifolds, provided the primary operations - addition and subtraction - are defined. Our motivation is primarily focused on state-estimation using non-Gaussian factor graphs for multimodal simultaneous localization and mapping in robotics. The paper presents the method as well as simulation and experimental results for validation. Our implementation is publicly available and allows for expansion with user-defined manifold mixtures.

© 2019 IEEE. The recent success of object detection systems motivates object-based representations for robot navigation; i.e. semantic simultaneous localization and mapping (SLAM). The semantic SLAM problem can be decomposed into a discrete inference problem: determining object class labels and measurement-landmark correspondences (the data association problem), and a continuous inference problem: obtaining the set of robot poses and object locations in the environment. A solution to the semantic SLAM problem necessarily addresses this joint inference, but under ambiguous data associations this is in general a non-Gaussian inference problem, while the majority of previous work focuses on Gaussian inference. Previous solutions to data association either produce solutions between potential hypotheses or maintain multiple explicit hypotheses for each association. We propose a solution that represents hypotheses as multiple modes of an equivalent non-Gaussian sensor model. We then solve the resulting non-Gaussian inference problem using nonparametric belief propagation. We validate our approach in a simulated hallway environment under a variety of sensor noise characteristics, as well as using real data from the KITTI dataset, demonstrating improved robustness to perceptual aliasing and odometry uncertainty.

Synthetic Aperture Sonar (SAS) is a technique to improve the spatial resolution from a moving set of receivers by extending the array in time, increasing the effective array length and aperture. This technique is limited by the accuracy of the receiver position estimates, necessitating highly accurate, typically expensive aided-inertial navigation systems for submerged platforms. We leverage simultaneous localization and mapping to fuse acoustic and navigational measurements and obtain accurate pose estimates even without the benefit of absolute positioning for lengthy underwater missions. We demonstrate a method of formulating the well-known SAS problem in a SLAM framework, using acoustic data from hydrophones to simultaneously estimate platform and beacon position. An empirical probability distribution is computed from a conventional beamformer to correctly account for uncertainty in the acoustic measurements. The non-parametric method relieves the familiar Gaussian-only assumption currently used in the localization and mapping discipline and fits effectively into a factor graph formulation with conventional factors such as ground-truth priors and odometry. We present results from field experiments performed on the Charles River with an autonomous surface vehicle which demonstrate simultaneous localization of an unknown acoustic beacon and vehicle positioning, and provide comparison to GPS ground truths.

We relax parametric inference to a nonparametric representation towards more general solutions on factor graphs. We use the Bayes tree factorization to maximally exploit structure in the joint posterior thereby minimizing computation. We use kernel density estimation to represent a wider class of constraint beliefs, which naturally encapsulates multi-hypothesis and non-Gaussian inference. A variety of new uncertainty models can now be directly applied in the factor graph, and have the solver recover a potentially multimodal posterior. For example, data association for loop closure proposals can be incorporated at inference time without further modifications to the factor graph. Our implementation of the presented algorithm is written entirely in the Julia language, exploiting high performance parallel computing. We show a larger scale use case with the well known Victoria park mapping and localization data set inferring over uncertain loop closures.

Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution September 2017, This thesis presents a sum-product inference algorithm for platform navigation called Multi-modal iSAM (incremental smoothing and mapping). CommonGaussian-only likelihoods are restrictive and require a complex front-end processes to deal with non-Gaussian measurements. Instead, our approach allows the front-end to defer ambiguities with non-Gaussian measurement models. We retain the acyclic Bayes tree (and incremental update strategy) from the predecessor iSAM2 maxproduct algorithm [Kaess et al., IJRR 2012]. The approach propagates continuous beliefs on the Bayes (Junction) tree, which is an efficient symbolic refactorization of the nonparametric factor graph, and asymptotically approximates the underlying Chapman-Kolmogorov equations. Our method tracks dominant modes in the marginal posteriors of all variables with minimal approximation error, while suppressing almost all lowlikelihood modes (in a non-permanent manner). Keeping with existing inertial navigation, we present a novel, continuous-time, retroactively calibrating inertial odometry residual function, using preintegration to seamlessly incorporate pure inertial sensor measurements into a factor graph. We centralize around a factor graph (with starved graph databases) to separate elements of the navigation into an ecosystem of processes. Practical examples are included, such as how to infer multi-modal marginal posterior belief estimates for ambiguous loop closures; rawbeam-formed acoustic measurements; or conventional parametric likelihoods, and others., This work was partially supported by the National Science Foundation under grant IIS-1318392 and by the Office of Naval Research under grant N00014-16-1- 2628.

The DARPA Robotics Challenge Trials held in December 2013 provided a landmark demonstration of dexterous mobile robots executing a variety of tasks aided by a remote human operator using only data from the robot's sensor suite transmitted over a constrained, field-realistic communications link. We describe the design considerations, architecture, implementation, and performance of the software that Team MIT developed to command and control an Atlas humanoid robot. Our design emphasized human interaction with an efficient motion planner, where operators expressed desired robot actions in terms of affordances fit using perception and manipulated in a custom user interface. We highlight several important lessons we learned while developing our system on a highly compressed schedule., United States. Defense Advanced Research Projects Agency (United States. Air Force Research Laboratory Award FA8750-12-1-0321), United States. Office of Naval Research (Award N00014-12-1-0071)

The DARPA Robotics Challenge Trials held in December 2013 provided a landmark demonstration of dexterous mobile robots executing a variety of tasks aided by a remote human operator using only data from the robot's sensor suite transmitted over a constrained, field-realistic communications link. We describe the design considerations, architecture, implementation and performance of the software that Team MIT developed to command and control an Atlas humanoid robot. Our design emphasized human interaction with an efficient motion planner, where operators expressed desired robot actions in terms of affordances fit using perception and manipulated in a custom user interface. We highlight several important lessons we learned while developing our system on a highly compressed schedule., Sponsored in part by ONR and DARPA.

A discontinuity seems to exist in present aided inertial navigation systems – the operational availability of high cost inertial navigation currently depends on the availability of a valid GPS lock. In general GPS solutions can be two or more orders cheaper than their inertial sensors counterparts. This paper addresses the north alignment by gyrocompassing in the context of more modern smoothing techniques. Incremental smoothing is becoming a serious contender for in-situ state estimation. The work here presents a probabilistic model for north alignment with an analysis towards the achievable accuracy of such a system. A pose graph formulation is used to estimate inertial sensor calibration terms over a long spanning trajectory, from which a true north alignment can be extracted. The preintegral method is used to condense high rate inertial data, but allow for post integration bias correction. Results show that the proposed alignment scheme is feasible, and would for gyrocompassing alignment relaxed sensor performance constraints

The DARPA Robotics Challenge Trials held in December 2013 provided a landmark demonstration of dexterous mobile robots executing a variety of tasks aided by a remote human operator using only data from the robot's sensor suite transmitted over a constrained, field-realistic communications link. We describe the design considerations, architecture, implementation and performance of the software that Team MIT developed to command and control an Atlas humanoid robot. Our design emphasized human interaction with an efficient motion planner, where operators expressed desired robot actions in terms of affordances fit using perception and manipulated in a custom user interface. We highlight several important lessons we learned while developing our system on a highly compressed schedule.